Emoji Response Prediction Using Two-Stage Sentiment Models
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Determining likely responses to electronic communications, particularly those containing non-textual content such as emojis, is challenging due to the nuanced and complex nature of human interaction, which can lead to unintended negative reactions.
Innovation Solution
A computing device processes messages using a first machine learning model to determine subsets of emojis based on sentiment, and a second model selects predicted responses from these subsets, trained on historical message data to improve response prediction accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If machine learning models are used to predict emoji responses, then response prediction accuracy is improved, but device complexity increases
Solution Approach 1:
The patent divides the emoji prediction task into two sequential stages: a first machine learning model (classifier) that determines emoji categories based on message sentiment, and a second machine learning model (regressor) that predicts specific emoji selections. This segmentation allows each model to specialize in one aspect, improving overall prediction accuracy while managing computational complexity through modular architecture.
Solution Approach 2:
The system performs preliminary sentiment analysis on the input message before generating emoji predictions. By first classifying the sentiment (positive, negative, neutral) and then using this classification to guide the emoji prediction, the system prepares the data in advance, which improves prediction accuracy and allows for more efficient two-stage processing.
2Measurement precision
If multiple machine learning models are used for sentiment analysis and emoji selection, then response prediction accuracy is improved, but processing time increases
Solution Approach 1:
The patent segments the prediction process into two independent sequential stages: sentiment classification using a first machine learning model, and emoji selection using a second machine learning model. This segmentation allows each model to be optimized for its specific task and enables parallel processing of different message types, reducing overall processing time while maintaining high accuracy.
Solution Approach 2:
The system performs sentiment classification as a preliminary action before emoji prediction. By pre-determining the sentiment category, the system can then efficiently select appropriate emojis without re-processing the entire message, thereby reducing redundant computational operations and decreasing total processing time.
Data Source
AI summary
Systems, methods, and apparatuses are described herein for performing sentiment analysis on electronic communications relating to one or more image-based communications methods, such as emoji. Message data may be received. The message data may correspond to a message that is intended to be sent but has not yet been sent to an application. Using a first machine learning model, one or more subsets of the plurality of emoji may be determined. The one or more subsets of the plurality of emoji may comprise one or more different types and quantities of emoji, and may each correspond to the same or a different sentiment. Using a second machine learning model, one or more emojis may be selected from the one or more subsets. The one or more emojis selected may correspond to responses to the message.